From external to internal regret

Journal of Machine Learning Research

Volumn 8, Issue , 2007, Pages 1307-1324

  Blum, Avrim ^a   Mansour, Yishay ^b  

^a Carnegie Mellon University   (United States)

^b TEL AVIV UNIVERSITY   (Israel)

Author keywords

External regret; Internal regret; Multi arm bandit; Online learning; Reductions; Sleeping experts

Indexed keywords

EXTERNAL REGRET; INTERNAL REGRET; MULTI-ARM BANDIT; ONLINE LEARNING; SLEEPING EXPERTS;

MATHEMATICAL MODELS; ONLINE SYSTEMS; PROBLEM SOLVING;

ALGORITHMS;

EID: 34547254640     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (29)

1. P. Auer, N. Cesa-Bianchi, Y. Freund, and R.E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002a.
2. P. Auer, N. Cesa-Bianchi, and C. Gentile. Adaptive and self-confident on-line learning algorithms. Journal of Computing and System Sciences, 64(1):48-75, 2002b.
3. R. J. Aumann. Subjectivity and correlation in randomized strategies. Journal of Mathematical Economics, 1:67-96, 1974.
4. D. Blackwell. An analog of the mimimax theorem for vector payoffs. Pacific Journal of Mathematics, 6:1-8, 1956.
5. A. Blum. Empirical support for Winnow and Weighted-Majority based algorithms: Results on a calendar scheduling domain. Machine Learning, 26:5-23, 1997.
6. N. Cesa-Bianchi, Y. Freund, D.P. Helmbold, D. Haussler, R.E. Schapire, and M.K. Warmuth. How to use expert advice. Journal of the Association for Computing Machinery (JACM), 44(3):427-485, 1997.
7. N. Cesa-Bianchi and G. Lugosi. Potential-based algorithms in on-line prediction and game theory. Machine Learning, 51(3):239-261, 2003.
8. N. Cesa-Bianchi, G. Lugosi, and G. Stoltz. Regret minimization under partial monitoring. Mathematics of Operations Research, 31:562-580, 2006.
9. N. Cesa-Bianchi, Y. Mansour, and G. Stoltz. Improved second-order bounds for prediction with expert advice. In Proceedings of the Eighteenth Annual Conference on Computational Learning Theory, pages 217-232, 2005.
10. W. Cohen and Y. Singer. Learning to query the web. In AAAI Workshop on Internet-Based Information Systems, 1996.
11. W. Cohen and Y. Singer. Context-sensitive learning methods for text categorization. ACM Transactions on Information Systems, 17(2):141-173, 1999.
12. W. Feller. An Introduction to Probability Theory and its Applications. - Vol. 1. Wiley, 1968.
13. W. Feller. An Introduction to Probability Theory and its Applications. - Vol. 2. Wiley, 1971.
14. D. Foster and R. Vohra. A randomization rule for selecting forecasts. Operations Research, 41(4): 704-709, July-August 1993.
15. D. Foster and R. Vohra. Calibrated learning and correlated equilibrium. Games and Economic Behavior, 21:40-55, 1997.
16. D. Foster and R. Vohra. Asymptotic calibration. Biometrika, 85:379-390, 1998.
17. D. Foster and R. Vohra. Regret in the on-line decision problem. Games and Economic Behavior, 29:7-36, 1999.
18. Y. Freund and R.E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119-139, 1997.
19. Y. Freund and R.E. Schapire. Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29:79-103, 1999.
20. Y. Freund, R.E. Schapire, Y. Singer, and M.K. Warmuth. Using and combining predictors that specialize. In Proceedings of the 29th Annual Symposium on Theory of Computing, pages 334-343, 1997.
21. J. Hannan. Approximation to Bayes risk in repeated plays. In M. Dresher, A. Tucker, and P. Wolfe, editors, Contributions to the Theory of Games, volume 3, pages 97-139. Princeton University Press, 1957.
22. S. Hart and A. Mas-Colell. A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68:1127-1150, 2000.
23. S. Hart and A. Mas-Colell. A reinforcement procedure leading to correlated equilibrium. In Wilhelm Neuefeind Gerard Debreu and Walter Trockel, editors, Economic Essays, pages 181-200. Springer, 2001.
24. E. Lehrer. A wide range no-regret theorem. Games and Economic Behavior, 42:101-115, 2003.
25. N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285-318, 1988.
26. N. Littlestone and M.K. Warmuth. The weighted majority algorithm. Information and Computation, 108:212-261, 1994.
27. G. Stoltz. Incomplete Information and Internal Regret in Prediction of Individual Sequences. PhD thesis, Dept. of Mathematics, University Paris XI, ORSAY, 2005.
28. G. Stoltz and G. Lugosi. Internal regret in on-line portfolio selection. Machine Learning, 59(1-2): 125-159, 2005.
29. G. Stoltz and G. Lugosi. Learning correlated equilibria in games with compact sets of strategies. Games and Economic Behavior, 59:187-209, 2007.